Evaluation and prediction of drilling wear based on machine vision

Surface wear of drilling bit in the drilling process is complex, and the traditional wear index is not suitable to reflect the wear condition of drilling bit well; it is necessary to investigate on the appropriate wear testing and evaluation method. In this paper, a visual measurement system is set...

Full description

Saved in:
Bibliographic Details
Published in:International journal of advanced manufacturing technology 2021-06, Vol.114 (7-8), p.2055-2074
Main Authors: Gu, Peng, Zhu, Chuanmin, Yu, Yiqing, Liu, Dinghao, Tao, Zhan, Wu, Yinyue
Format: Article
Language:English
Subjects:
CAE) and Design
Computer-Aided Engineering (CAD
Diameters
Drill bits
Drilling machines (tools)
Engineering
Evaluation
Feature extraction
Image segmentation
Indicators
Industrial and Production Engineering
Machine vision
Mechanical Engineering
Media Management
Original Article
Prediction models
Principal components analysis
Support vector machines
Vision systems
Wear mechanisms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Surface wear of drilling bit in the drilling process is complex, and the traditional wear index is not suitable to reflect the wear condition of drilling bit well; it is necessary to investigate on the appropriate wear testing and evaluation method. In this paper, a visual measurement system is set up to obtain the drilling bit wear characteristics based on machine vision. The wear area image is grayscale processed, and the gray image is thresholding segmentation processed, then the boundary feature is extracted based on the chain code method. A comprehensive evaluation system is established, in which the wear perimeter, the equivalent wear diameter, and maximum wear width of different areas are proposed as the wear indicators. The wear fusion feature based on the principal component analysis is proposed to characterize the drilling bit wear degree, the wear indicators of different regions are characterized and fused as the wear degree of different regions, then the prediction model of the drilling bit wear degree is established based on support vector machine. The results show that the predicted results are mainly consistent with the experimental results. The research of the drilling bit wear characteristics based on principal component analysis can provide guidance for the study of drilling bit wear mechanism.
ISSN:0268-3768
1433-3015
DOI:10.1007/s00170-021-06887-w